Main Content

densenet201

DenseNet-201 convolutional neural network

collapse all in page
  • DenseNet-201 network architecture

Syntax

net = densenet201
net = densenet201('Weights','imagenet')
lgraph = densenet201('Weights','none')

Description

DenseNet-201 is a convolutional neural network that is 201 layers deep. You can load a pretrained version of the network trained on more than a million images from the ImageNet database [1]. The pretrained network can classify images into 1000 object categories, such as keyboard, mouse, pencil, and many animals. As a result, the network has learned rich feature representations for a wide range of images. The network has an image input size of 224-by-224. For more pretrained networks in MATLAB®, see Pretrained Deep Neural Networks.

You can use classify to classify new images using the DenseNet-201 model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with DenseNet-201.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images and load DenseNet-201 instead of GoogLeNet.

example

net = densenet201 returns a DenseNet-201 network trained on the ImageNet data set.

This function requires the Deep Learning Toolbox™ Model for DenseNet-201 Network support package. If this support package is not installed, then the function provides a download link.

net = densenet201('Weights','imagenet') returns a DenseNet-201 network trained on the ImageNet data set. This syntax is equivalent to net = densenet201.

lgraph = densenet201('Weights','none') returns the untrained DenseNet-201 network architecture. The untrained model does not require the support package.

Examples

collapse all

Download and install the Deep Learning Toolbox Model for DenseNet-201 Network support package.

Type densenet201 at the command line.

densenet201

If the Deep Learning Toolbox Model for DenseNet-201 Network support package is not installed, then the function provides a link to the required support package in the Add-On Explorer. To install the support package, click the link, and then click Install. Check that the installation is successful by typing densenet201 at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

densenet201
ans = 

  DAGNetwork with properties:

         Layers: [709×1 nnet.cnn.layer.Layer]
    Connections: [806×2 table]

Visualize the network using Deep Network Designer. 

deepNetworkDesigner(densenet201)

Explore other pretrained neural networks in Deep Network Designer by clicking New.

Deep Network Designer start page showing available pretrained neural networks

If you need to download a neural network, pause on the desired neural network and click Install to open the Add-On Explorer.

Output Arguments

collapse all

Pretrained DenseNet-201 convolutional neural network, returned as a DAGNetwork object.

Untrained DenseNet-201 convolutional neural network architecture, returned as a LayerGraph object.

References

[1] ImageNet. http://www.image-net.org

[2] Huang, Gao, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. "Densely Connected Convolutional Networks." In CVPR, vol. 1, no. 2, p. 3. 2017.

Extended Capabilities

Version History

Introduced in R2018a

See Also

| | | | | | | | | | | |

Topics